Sort by
Refine Your Search
-
Listed
-
Category
-
Country
-
Employer
- CNRS
- Nature Careers
- University of Nottingham
- Technical University of Munich
- Aalborg University
- Empa
- Forschungszentrum Jülich
- NTNU - Norwegian University of Science and Technology
- University of Luxembourg
- Aalborg Universitet
- DAAD
- Delft University of Technology (TU Delft)
- Helmholtz-Zentrum Hereon
- Inria, the French national research institute for the digital sciences
- KU LEUVEN
- Linköping University
- Newcastle University
- Northeastern University London
- University of Twente
- Utrecht University
- Vrije Universiteit Brussel (VUB)
- BRGM
- CEA
- CNRS UMR6614 CORIA
- Centrale Supelec
- Cranfield University
- ETH Zürich
- Eberhard Karls University Tübingen
- Fundació per a la Universitat Oberta de Catalunya
- Graz University of Technology
- Grenoble INP - Institute of Engineering
- Helmholtz Zentrum Hereon
- Helmholtz Zentrum München - Deutsches Forschungszentrum für Gesundheit und Umwelt
- IMDEA Networks Institute
- INRIA
- Institut de Recherche pour le Développement (IRD)
- Instituto de Tecnología Química
- International PhD Programme (IPP) Mainz
- Jagiellonian University
- LEM3
- Loughborough University;
- Monash University
- NTNU Norwegian University of Science and Technology
- Newcastle University;
- Oak Ridge National Laboratory
- Oxford Brookes University
- Radboud University Medical Center (Radboudumc)
- Technical University of Denmark
- Technische Universität Berlin •
- The Max Planck Institute for Neurobiology of Behavior – caesar •
- The University of Chicago
- Umeå University
- University of Amsterdam (UvA)
- University of Birmingham;
- University of Cambridge;
- University of Cyprus
- University of Exeter
- University of Greenwich
- University of Göttingen •
- University of Oxford
- University of Plymouth
- University of South-Eastern Norway
- University of Southampton
- cnrs
- 54 more »
- « less
-
Field
-
, and rigorously evaluate machine learning and deep learning models (CNNs, DNNs, transformers, graph neural networks, diffusion models, multimodal models, reinforcement learning) as well as software
-
investigate deep learning architectures capable of learning microstructure-property mappings, including convolutional neural networks for microstructure image analysis, graph-based representations
-
. The research will focus on identifying and characterizing ultrasonic signatures emitted by aging electronic components, and on developing physics-informed neural networks (PINNs) to model their degradation
-
learning-powered algorithms as well as hybrid approaches, combining either reinforcement learning or deep learning (Graph Neural Networks) with human-based modelling, for fully flawless and autonomous method
-
of current systems. Considering this, memristors are innovative electronic components that enable the creation of hardware neural networks inspired by the brain, potentially reducing the energy consumption
-
. 2) the development of computational models to enquire about the mechanisms that enable heterogeneous representations in neural networks. These models will be informed by experimental data. Duties
-
external funding to cover international fees. References: R. Fedorov, A. Nihei, G. Gryn’ova, Multi-Solvent Graph Neural Network for Reduction Potential Prediction across the Chemical Space, J. Chem. Inf
-
modelling, data assimilation, and multi-scale neural network architectures applied to spatio-temporal data. The development of these methods is motivated by a concrete and important application: inferring gas
-
computing and decentralized intelligence where a swarm of nodes learns graph dependencies by effectively integrating the structure of distributed systems into neural network architecture. This approach
-
science, applied mathematics, physics or a similar area very good programming skills in Python good prior experience with neural networks using common Python-ML libraries such as PyTorch background knowledge in